agent-native-docs

How to look up version-matched Agent-Native framework docs and source in node_modules. Use before coding against @agent-native/core APIs or advanced features.

Quality

78%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Failed to scan

The risk profile of this skill

Fix and improve this skill with Tessl

tessl review fix ./packages/core/docs/SKILL.md

Quality

Content

93%Weight 40%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The body is a tight, highly actionable lookup workflow with concrete commands, a clear sequence, and a clean section structure that earns top conciseness, actionability, and progressive-disclosure marks. The only gap is the absence of an explicit verification step confirming the docs version matches the installed package.

Suggestions

Add a verification checkpoint in the How sequence (e.g. after locating docs, confirm the doc version matches the installed @agent-native/core version before relying on it) to raise workflow_clarity to 5.

Make the step-6 fallback branch explicit as an 'if/else' rather than a bare step so the conditional flow is unmistakable.

Dimension	Reasoning	Score
Conciseness	Lean and efficient — every line is a concrete command or a terse directive with no explanations of concepts Claude already knows, matching 'lean and efficient; assumes Claude's competence'; the slight Rule/How overlap is not enough to drop to 4.	5 / 5
Actionability	Fully executable, copy-pasteable commands throughout (pnpm action framework-search/docs-search/source-search with real flags, plus an rg fallback against a real node_modules path), covering search, specific-page read, source examples, and the fallback case, matching the 5 anchor.	5 / 5
Workflow Clarity	A clear numbered 1-7 sequence with an explicit fallback branch (step 6) and extension (step 7); not 5 because there is no verification checkpoint confirming the located doc matches the installed @agent-native/core version — the exact failure this skill guards against. The destructive/batch validation cap does not apply since this is a read-only lookup skill, so it stays at 4 rather than being capped at 3.	4 / 5
Progressive Disclosure	Under 50 lines with no bundle files and no external references, organized into clear sections (Rule, How, Useful Slugs table, Don't); per the rubric's simple-skill exception, this is a 5 for a well-organized sub-50-line skill needing no external file references.	5 / 5
	Total	19 / 20 Passed

Description

62%Weight 40%Scale 1-5

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

The description clearly states both what the skill does and when to use it, anchored to a specific framework package, which keeps conflict risk low. Its weakness is modest specificity and trigger-term breadth — it names one action and relies on package jargon rather than diverse natural phrasing.

Suggestions

List 2-3 concrete actions (e.g. 'search docs by slug, query source examples, read a specific doc page') so specificity reaches the 5 anchor.

Broaden trigger terms with plain synonyms like 'Agent-Native framework' alongside the scoped '@agent-native/core' package name.

Add an explicit version-matching trigger phrase (e.g. 'Use when the installed @agent-native/core version matters') to push completeness toward 5.

Dimension	Reasoning	Score
Specificity	Names the domain (Agent-Native docs/source) and one concrete action ("look up version-matched… docs and source in node_modules") tied to the specific package @agent-native/core, but does not enumerate several distinct actions, so it sits at the '1-2 concrete actions' anchor rather than 4.	3 / 5
Completeness	Explicitly answers both what (look up version-matched docs and source) and when ("Use before coding against @agent-native/core APIs or advanced features"), matching the 'has both what and when; when could be more explicit' anchor; not 5 because the trigger phrasing lacks the rich synonym coverage of the 5 anchor.	4 / 5
Trigger Term Quality	Has a natural trigger clause ("Use before coding against @agent-native/core APIs or advanced features") plus "version-matched… docs", but leans on the scoped package jargon @agent-native/core and omits the plain 'Agent-Native' phrasing and synonym variants users would more naturally say, fitting 'some relevant keywords but missing common variations' rather than 4.	3 / 5
Distinctiveness Conflict Risk	Tied to a specific framework package and node_modules/@agent-native/core path, giving it a clear niche with low conflict risk, matching 'mostly distinct; minor overlap risk with closely related skills'; not 5 because a sibling Agent-Native source/docs skill could still overlap.	4 / 5
	Total	14 / 20 Passed

Validation

100%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: BuilderIO/agent-native
Path: packages/core/docs/SKILL.md
Commit: b0df876

Reviewed: 5 days ago

Table of Contents

Discovery Implementation Validation

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.